Intel 3rd Gen Xeon Scalable (Ice Lake SP) Review: Generationally Big, Competitively Small
by Andrei Frumusanu on April 6, 2021 11:00 AM EST- Posted in
- Servers
- CPUs
- Intel
- Xeon
- Enterprise
- Xeon Scalable
- Ice Lake-SP
SPEC - Single-Threaded Performance
Single-thread performance of server CPUs usually isn’t the most important metric for most scale-out workloads, but there are use-cases such as EDA tools which are pretty much single-thread performance bound.
Power envelopes here usually don’t matter, and what is actually the performance factor that comes at play here is simply the boost clocks of the CPUs as well as the IPC improvement, and memory latency of the cores.
The one hiccup for the Xeon 8380 this generation is the fact that although there’s plenty of IPC gains to be had compared to previous microarchitectures, the new SKU is only boosting up to 3.4GHz, whereas the 8280 was able to boost up to 4GHz, which is a 15% deficit.
Even with the clock frequency disadvantage, thanks to the IPC gains, much improved memory bandwidth, as well as the much larger L3 cache, the new Ice Lake part to most of the time beat the Cascade Lake part, with only a couple of compute-bound core workloads where it falls behind.
The floating-point figures are more favourable to the ICX architecture due to the stronger memory performance.
Overall, the new Xeon 8380 at least manages to post slight single-threaded performance increases this generation, with larger gains in memory-bound workloads. The 8380 is essentially on par with AMD’s 7763, and loses out to the higher frequency optimised parts.
Intel has a few SKUs which offers slightly higher ST boost clocks of up to 3.7GHz – 300Mhz / 8.8% higher than the 8380, however that part is only 8-core and features only 18MB of cache. Other SKUS offer 3.5-3.6GHz boosts, but again less cache. So while the ST figures here could improve a bit on those parts, it’s unlikely to be significant.
169 Comments
View All Comments
Gondalf - Wednesday, April 7, 2021 - link
Depends on workload. If you need of a massive per core bandwidth, there is only a street: Intel.If you need of very low cache latency, there is only a street: Intel.
Moreover consider that actually AMD is selling a small number of 64 cores SKUs, the focus of the market is on 32 cores parts. So again in this arena Intel is absolutely the best for bandwidth, latencies and idle power (AMD main defect).
Not much is changed, Amd is best for many cores apps, Intel for medium/low number of cores apps.
Something will change at the end of this year.
SarahKerrigan - Tuesday, April 6, 2021 - link
So the 8380 number is being used for both Ice-SP and Cooper-SP, which are totally unrelated designs, on different platforms, with different microarchitectures?Well, that's not confusing at all.
Drumsticks - Tuesday, April 6, 2021 - link
I thought surely it must have been a typo or you were confused, but yes indeed, you can find the 40 core 8380 right next to the 28 core 14nm 8380HL.Intel's naming has never been stellar but this is a new level.
jeremyshaw - Tuesday, April 6, 2021 - link
Cooper Lake probably existed about as much as Cannon Lake. Intel still doesn't want to acknowledge their failures.This totally bodes well. /s
schujj07 - Tuesday, April 6, 2021 - link
You can actually buy Cooper Lake 4p servers.fallaha56 - Tuesday, April 6, 2021 - link
well you won't be buying 38-40 core Ice Lake onesphantom parts, yield are awfuls. and as we saw, on the lower core count parts, so is performance
fallaha56 - Tuesday, April 6, 2021 - link
https://semiaccurate.com/2021/04/06/intels-ice-lak...29a - Wednesday, April 7, 2021 - link
Are you getting paid for every semiaccurate link you post?eastcoast_pete - Tuesday, April 6, 2021 - link
Maybe that's what Intel meant with "improved cryptographic performance"; nobody can make any sense out of their naming scheme (: . Cryptic indeed!amootpoint - Tuesday, April 6, 2021 - link
It seems like a great wholistic platform. I must say, well done Intel.